Arao AI
Back to search results

Hy-Memory-30B-A3B · IQ1_S

Start a discussion
NVIDIA H2097GBStrata v0.30L2 Cross-framework verified

This page aggregates 1 real-world runs of Hy-Memory-30B-A3B (IQ1_S) on NVIDIA H20 with Strata, contributed by 1 independent source platforms; metrics are averages of published measurements.

178.17 tok/s

Decode

Decode speed

571.19 tok/s

Prefill

Prefill speed

2.45 s

TTFT

Time to first token

28.56 GB

VRAM

VRAM usage

L2 Cross-framework verified

1

Measured runs

1

Independent sources

Other

Source platforms

16 days ago

Last verified

Performance

  1. llama.cpp · Q6_K Decode 57.59 · Prefill 253.97 ·
  2. Strata · IQ1_S (current)Decode 178.17 · Prefill 571.19 ·
  3. Strata · IQ3_XS Decode 139.08 · Prefill 595.25 ·

Core figures

Decode (avg)
178.17 tok/s
Prefill (avg)
571.19 tok/s
TTFT (avg)
2.45 s
VRAM (avg)
28.56 GB
MTP acceptance rate
0.68
TTFB
1.43 GB
Power draw
315.4 W

Configuration

Member-level fields are taken from the most recent run

Model
Hy-Memory-30B-A3B
Quantization
IQ1_S
Framework
Strata
Version
v0.30
Context length
16384 tokens
Batch size
256
GPU layers
12
Flash Attention
On

Hardware

Nominal and measured figures are shown side by side; whether it runs is the reader's call

GPU
NVIDIA H20
Nominal VRAM
97 GB
Measured VRAM (avg)
28.56 GB
OS
Ubuntu 24.04
Driver
570.86
CUDA
12.6
Power draw
315.4 W

Get started

Original model resources

Base model resources may not match this quantization. Use the verified deployment weights above when available.

Sources & evidence

1 measured records in total, each traceable to its original source

  1. L2 Cross-framework verifiedOtherOriginal link Verified on 2026-10-19

    v0.30 · Ubuntu 24.04 · CUDA 12.6 · 16384 ctx

    178.17 tok/s

    Decode

    571.19 tok/s

    Prefill

    2.45 s

    TTFT

    28.56 GB

    VRAM

    0.68

    MTP

    315.4 W

    Power draw

    L2 batch seed 2026-10-19: Strata on hw_id=56 running model_id=87 at IQ1_S